In this work, we propose a channel allocation and power control algorithm for energy harvesting (EH) device-to-device (D2D)\ncommunication based on nonorthogonal multiple access (NOMA). The algorithm considers usersâ?? quality of service (QoS) and\nenergy causality constraint to maximize the total capacity of D2D groups. The optimal offline allocation of channel and power is\nrealized firstly. Then, the offline optimization results are taken as the training dataset to train the neural network to obtain the\noptimal model of the transmission power. The online power allocation optimization algorithm is further proposed. Simulation\nresults show that the offline algorithm can improve the total capacity of D2D groups, and the performance of the online algorithm\nis close to the offline algorithm.
Loading....